© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9197
    Prev
    Next
    INDEX
    Explanations

    places, organizations, and events

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     MainAxisSize
    -0.67
    thâu
    -0.65
     دیکھیے
    -0.61
    WriteAttribute
    -0.60
     Normdatei
    -0.59
    enterOuterAlt
    -0.59
    fromnode
    -0.59
     booths
    -0.58
     createState
    -0.57
     surla
    -0.57
    POSITIVE LOGITS
     letter
    0.59
     dévelo
    0.51
     dieux
    0.50
     Justiça
    0.50
    Letter
    0.50
     églises
    0.50
    letter
    0.49
     letters
    0.49
    afin
    0.47
     LETTER
    0.47
    Activations Density 7.844%

    No Known Activations